Merge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/shli/md

Pull MD fixes from Shaohua Li:
 "This fixes several bugs, three of them are marked for stable:

   - an initialization issue fixed by Ming

   - a bio clone race issue fixed by me

   - an async tx flush issue fixed by Ofer

   - other cleanups"

* 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/shli/md:
  MD: fix warnning for UP case
  md/raid5: add thread_group worker async_tx_issue_pending_all
  md: simplify code with bio_io_error
  md/raid1: fix writebehind bio clone
  md: raid1-10: move raid1/raid10 common code into raid1-10.c
  md: raid1/raid10: initialize bvec table via bio_add_page()
  md: remove 'idx' from 'struct resync_pages'

drivers/md/md.c

@@ -2287,7 +2287,7 @@ static void export_array(struct mddev *mddev)
 
 static bool set_in_sync(struct mddev *mddev)
 {
-	WARN_ON_ONCE(!spin_is_locked(&mddev->lock));
+	WARN_ON_ONCE(NR_CPUS != 1 && !spin_is_locked(&mddev->lock));
 	if (!mddev->in_sync) {
 		mddev->sync_checkers++;
 		spin_unlock(&mddev->lock);

drivers/md/md.h

@@ -731,58 +731,4 @@ static inline void mddev_check_write_zeroes(struct mddev *mddev, struct bio *bio
 	    !bdev_get_queue(bio->bi_bdev)->limits.max_write_zeroes_sectors)
 		mddev->queue->limits.max_write_zeroes_sectors = 0;
 }
-
-/* Maximum size of each resync request */
-#define RESYNC_BLOCK_SIZE (64*1024)
-#define RESYNC_PAGES ((RESYNC_BLOCK_SIZE + PAGE_SIZE-1) / PAGE_SIZE)
-
-/* for managing resync I/O pages */
-struct resync_pages {
-	unsigned	idx;	/* for get/put page from the pool */
-	void		*raid_bio;
-	struct page	*pages[RESYNC_PAGES];
-};
-
-static inline int resync_alloc_pages(struct resync_pages *rp,
-				     gfp_t gfp_flags)
-{
-	int i;
-
-	for (i = 0; i < RESYNC_PAGES; i++) {
-		rp->pages[i] = alloc_page(gfp_flags);
-		if (!rp->pages[i])
-			goto out_free;
-	}
-
-	return 0;
-
-out_free:
-	while (--i >= 0)
-		put_page(rp->pages[i]);
-	return -ENOMEM;
-}
-
-static inline void resync_free_pages(struct resync_pages *rp)
-{
-	int i;
-
-	for (i = 0; i < RESYNC_PAGES; i++)
-		put_page(rp->pages[i]);
-}
-
-static inline void resync_get_all_pages(struct resync_pages *rp)
-{
-	int i;
-
-	for (i = 0; i < RESYNC_PAGES; i++)
-		get_page(rp->pages[i]);
-}
-
-static inline struct page *resync_fetch_page(struct resync_pages *rp,
-					     unsigned idx)
-{
-	if (WARN_ON_ONCE(idx >= RESYNC_PAGES))
-		return NULL;
-	return rp->pages[idx];
-}
 #endif /* _MD_MD_H */

drivers/md/raid1-10.c

@@ -0,0 +1,81 @@
+/* Maximum size of each resync request */
+#define RESYNC_BLOCK_SIZE (64*1024)
+#define RESYNC_PAGES ((RESYNC_BLOCK_SIZE + PAGE_SIZE-1) / PAGE_SIZE)
+
+/* for managing resync I/O pages */
+struct resync_pages {
+	void		*raid_bio;
+	struct page	*pages[RESYNC_PAGES];
+};
+
+static inline int resync_alloc_pages(struct resync_pages *rp,
+				     gfp_t gfp_flags)
+{
+	int i;
+
+	for (i = 0; i < RESYNC_PAGES; i++) {
+		rp->pages[i] = alloc_page(gfp_flags);
+		if (!rp->pages[i])
+			goto out_free;
+	}
+
+	return 0;
+
+out_free:
+	while (--i >= 0)
+		put_page(rp->pages[i]);
+	return -ENOMEM;
+}
+
+static inline void resync_free_pages(struct resync_pages *rp)
+{
+	int i;
+
+	for (i = 0; i < RESYNC_PAGES; i++)
+		put_page(rp->pages[i]);
+}
+
+static inline void resync_get_all_pages(struct resync_pages *rp)
+{
+	int i;
+
+	for (i = 0; i < RESYNC_PAGES; i++)
+		get_page(rp->pages[i]);
+}
+
+static inline struct page *resync_fetch_page(struct resync_pages *rp,
+					     unsigned idx)
+{
+	if (WARN_ON_ONCE(idx >= RESYNC_PAGES))
+		return NULL;
+	return rp->pages[idx];
+}
+
+/*
+ * 'strct resync_pages' stores actual pages used for doing the resync
+ *  IO, and it is per-bio, so make .bi_private points to it.
+ */
+static inline struct resync_pages *get_resync_pages(struct bio *bio)
+{
+	return bio->bi_private;
+}
+
+/* generally called after bio_reset() for reseting bvec */
+static void md_bio_reset_resync_pages(struct bio *bio, struct resync_pages *rp,
+			       int size)
+{
+	int idx = 0;
+
+	/* initialize bvec table again */
+	do {
+		struct page *page = resync_fetch_page(rp, idx);
+		int len = min_t(int, size, PAGE_SIZE);
+
+		/*
+		 * won't fail because the vec table is big
+		 * enough to hold all these pages
+		 */
+		bio_add_page(bio, page, len, 0);
+		size -= len;
+	} while (idx++ < RESYNC_PAGES && size > 0);
+}

drivers/md/raid1.c

@@ -81,14 +81,7 @@ static void lower_barrier(struct r1conf *conf, sector_t sector_nr);
 #define raid1_log(md, fmt, args...)				\
 	do { if ((md)->queue) blk_add_trace_msg((md)->queue, "raid1 " fmt, ##args); } while (0)
 
-/*
- * 'strct resync_pages' stores actual pages used for doing the resync
- *  IO, and it is per-bio, so make .bi_private points to it.
- */
-static inline struct resync_pages *get_resync_pages(struct bio *bio)
-{
-	return bio->bi_private;
-}
+#include "raid1-10.c"
 
 /*
  * for resync bio, r1bio pointer can be retrieved from the per-bio
@@ -170,7 +163,6 @@ static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data)
 			resync_get_all_pages(rp);
 		}
 
-		rp->idx = 0;
 		rp->raid_bio = r1_bio;
 		bio->bi_private = rp;
 	}
@@ -492,10 +484,6 @@ static void raid1_end_write_request(struct bio *bio)
 	}
 
 	if (behind) {
-		/* we release behind master bio when all write are done */
-		if (r1_bio->behind_master_bio == bio)
-			to_put = NULL;
-
 		if (test_bit(WriteMostly, &rdev->flags))
 			atomic_dec(&r1_bio->behind_remaining);
 
@@ -802,8 +790,7 @@ static void flush_bio_list(struct r1conf *conf, struct bio *bio)
 		bio->bi_next = NULL;
 		bio->bi_bdev = rdev->bdev;
 		if (test_bit(Faulty, &rdev->flags)) {
-			bio->bi_status = BLK_STS_IOERR;
-			bio_endio(bio);
+			bio_io_error(bio);
 		} else if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
 				    !blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
 			/* Just ignore it */
@@ -1088,7 +1075,7 @@ static void unfreeze_array(struct r1conf *conf)
 	wake_up(&conf->wait_barrier);
 }
 
-static struct bio *alloc_behind_master_bio(struct r1bio *r1_bio,
+static void alloc_behind_master_bio(struct r1bio *r1_bio,
 					   struct bio *bio)
 {
 	int size = bio->bi_iter.bi_size;
@@ -1098,11 +1085,13 @@ static struct bio *alloc_behind_master_bio(struct r1bio *r1_bio,
 
 	behind_bio = bio_alloc_mddev(GFP_NOIO, vcnt, r1_bio->mddev);
 	if (!behind_bio)
-		goto fail;
+		return;
 
 	/* discard op, we don't support writezero/writesame yet */
-	if (!bio_has_data(bio))
+	if (!bio_has_data(bio)) {
+		behind_bio->bi_iter.bi_size = size;
 		goto skip_copy;
+	}
 
 	while (i < vcnt && size) {
 		struct page *page;
@@ -1123,14 +1112,13 @@ skip_copy:
 	r1_bio->behind_master_bio = behind_bio;;
 	set_bit(R1BIO_BehindIO, &r1_bio->state);
 
-	return behind_bio;
+	return;
 
 free_pages:
 	pr_debug("%dB behind alloc failed, doing sync I/O\n",
 		 bio->bi_iter.bi_size);
 	bio_free_pages(behind_bio);
-fail:
-	return behind_bio;
+	bio_put(behind_bio);
 }
 
 struct raid1_plug_cb {
@@ -1483,7 +1471,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 			    (atomic_read(&bitmap->behind_writes)
 			     < mddev->bitmap_info.max_write_behind) &&
 			    !waitqueue_active(&bitmap->behind_wait)) {
-				mbio = alloc_behind_master_bio(r1_bio, bio);
+				alloc_behind_master_bio(r1_bio, bio);
 			}
 
 			bitmap_startwrite(bitmap, r1_bio->sector,
@@ -1493,14 +1481,11 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 			first_clone = 0;
 		}
 
-		if (!mbio) {
-			if (r1_bio->behind_master_bio)
-				mbio = bio_clone_fast(r1_bio->behind_master_bio,
-						      GFP_NOIO,
-						      mddev->bio_set);
-			else
-				mbio = bio_clone_fast(bio, GFP_NOIO, mddev->bio_set);
-		}
+		if (r1_bio->behind_master_bio)
+			mbio = bio_clone_fast(r1_bio->behind_master_bio,
+					      GFP_NOIO, mddev->bio_set);
+		else
+			mbio = bio_clone_fast(bio, GFP_NOIO, mddev->bio_set);
 
 		if (r1_bio->behind_master_bio) {
 			if (test_bit(WriteMostly, &conf->mirrors[i].rdev->flags))
@@ -2086,10 +2071,7 @@ static void process_checks(struct r1bio *r1_bio)
 	/* Fix variable parts of all bios */
 	vcnt = (r1_bio->sectors + PAGE_SIZE / 512 - 1) >> (PAGE_SHIFT - 9);
 	for (i = 0; i < conf->raid_disks * 2; i++) {
-		int j;
-		int size;
 		blk_status_t status;
-		struct bio_vec *bi;
 		struct bio *b = r1_bio->bios[i];
 		struct resync_pages *rp = get_resync_pages(b);
 		if (b->bi_end_io != end_sync_read)
@@ -2098,8 +2080,6 @@ static void process_checks(struct r1bio *r1_bio)
 		status = b->bi_status;
 		bio_reset(b);
 		b->bi_status = status;
-		b->bi_vcnt = vcnt;
-		b->bi_iter.bi_size = r1_bio->sectors << 9;
 		b->bi_iter.bi_sector = r1_bio->sector +
 			conf->mirrors[i].rdev->data_offset;
 		b->bi_bdev = conf->mirrors[i].rdev->bdev;
@@ -2107,15 +2087,8 @@ static void process_checks(struct r1bio *r1_bio)
 		rp->raid_bio = r1_bio;
 		b->bi_private = rp;
 
-		size = b->bi_iter.bi_size;
-		bio_for_each_segment_all(bi, b, j) {
-			bi->bv_offset = 0;
-			if (size > PAGE_SIZE)
-				bi->bv_len = PAGE_SIZE;
-			else
-				bi->bv_len = size;
-			size -= PAGE_SIZE;
-		}
+		/* initialize bvec table again */
+		md_bio_reset_resync_pages(b, rp, r1_bio->sectors << 9);
 	}
 	for (primary = 0; primary < conf->raid_disks * 2; primary++)
 		if (r1_bio->bios[primary]->bi_end_io == end_sync_read &&
@@ -2366,8 +2339,6 @@ static int narrow_write_error(struct r1bio *r1_bio, int i)
 			wbio = bio_clone_fast(r1_bio->behind_master_bio,
 					      GFP_NOIO,
 					      mddev->bio_set);
-			/* We really need a _all clone */
-			wbio->bi_iter = (struct bvec_iter){ 0 };
 		} else {
 			wbio = bio_clone_fast(r1_bio->master_bio, GFP_NOIO,
 					      mddev->bio_set);
@@ -2619,6 +2590,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 	int good_sectors = RESYNC_SECTORS;
 	int min_bad = 0; /* number of sectors that are bad in all devices */
 	int idx = sector_to_idx(sector_nr);
+	int page_idx = 0;
 
 	if (!conf->r1buf_pool)
 		if (init_resync(conf))
@@ -2846,7 +2818,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 			bio = r1_bio->bios[i];
 			rp = get_resync_pages(bio);
 			if (bio->bi_end_io) {
-				page = resync_fetch_page(rp, rp->idx++);
+				page = resync_fetch_page(rp, page_idx);
 
 				/*
 				 * won't fail because the vec table is big
@@ -2858,7 +2830,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 		nr_sectors += len>>9;
 		sector_nr += len>>9;
 		sync_blocks -= (len>>9);
-	} while (get_resync_pages(r1_bio->bios[disk]->bi_private)->idx < RESYNC_PAGES);
+	} while (++page_idx < RESYNC_PAGES);
 
 	r1_bio->sectors = nr_sectors;
 

drivers/md/raid10.c

@@ -110,14 +110,7 @@ static void end_reshape(struct r10conf *conf);
 #define raid10_log(md, fmt, args...)				\
 	do { if ((md)->queue) blk_add_trace_msg((md)->queue, "raid10 " fmt, ##args); } while (0)
 
-/*
- * 'strct resync_pages' stores actual pages used for doing the resync
- *  IO, and it is per-bio, so make .bi_private points to it.
- */
-static inline struct resync_pages *get_resync_pages(struct bio *bio)
-{
-	return bio->bi_private;
-}
+#include "raid1-10.c"
 
 /*
  * for resync bio, r10bio pointer can be retrieved from the per-bio
@@ -221,7 +214,6 @@ static void * r10buf_pool_alloc(gfp_t gfp_flags, void *data)
 			resync_get_all_pages(rp);
 		}
 
-		rp->idx = 0;
 		rp->raid_bio = r10_bio;
 		bio->bi_private = rp;
 		if (rbio) {
@@ -913,8 +905,7 @@ static void flush_pending_writes(struct r10conf *conf)
 			bio->bi_next = NULL;
 			bio->bi_bdev = rdev->bdev;
 			if (test_bit(Faulty, &rdev->flags)) {
-				bio->bi_status = BLK_STS_IOERR;
-				bio_endio(bio);
+				bio_io_error(bio);
 			} else if (unlikely((bio_op(bio) ==  REQ_OP_DISCARD) &&
 					    !blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
 				/* Just ignore it */
@@ -1098,8 +1089,7 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule)
 		bio->bi_next = NULL;
 		bio->bi_bdev = rdev->bdev;
 		if (test_bit(Faulty, &rdev->flags)) {
-			bio->bi_status = BLK_STS_IOERR;
-			bio_endio(bio);
+			bio_io_error(bio);
 		} else if (unlikely((bio_op(bio) ==  REQ_OP_DISCARD) &&
 				    !blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
 			/* Just ignore it */
@@ -2087,8 +2077,8 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 		rp = get_resync_pages(tbio);
 		bio_reset(tbio);
 
-		tbio->bi_vcnt = vcnt;
-		tbio->bi_iter.bi_size = fbio->bi_iter.bi_size;
+		md_bio_reset_resync_pages(tbio, rp, fbio->bi_iter.bi_size);
+
 		rp->raid_bio = r10_bio;
 		tbio->bi_private = rp;
 		tbio->bi_iter.bi_sector = r10_bio->devs[i].addr;
@@ -2853,6 +2843,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 	sector_t sectors_skipped = 0;
 	int chunks_skipped = 0;
 	sector_t chunk_mask = conf->geo.chunk_mask;
+	int page_idx = 0;
 
 	if (!conf->r10buf_pool)
 		if (init_resync(conf))
@@ -3355,7 +3346,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 			break;
 		for (bio= biolist ; bio ; bio=bio->bi_next) {
 			struct resync_pages *rp = get_resync_pages(bio);
-			page = resync_fetch_page(rp, rp->idx++);
+			page = resync_fetch_page(rp, page_idx);
 			/*
 			 * won't fail because the vec table is big enough
 			 * to hold all these pages
@@ -3364,7 +3355,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 		}
 		nr_sectors += len>>9;
 		sector_nr += len>>9;
-	} while (get_resync_pages(biolist)->idx < RESYNC_PAGES);
+	} while (++page_idx < RESYNC_PAGES);
 	r10_bio->sectors = nr_sectors;
 
 	while (biolist) {

drivers/md/raid5.c

@@ -3381,9 +3381,8 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 			sh->dev[i].sector + STRIPE_SECTORS) {
 			struct bio *nextbi = r5_next_bio(bi, sh->dev[i].sector);
 
-			bi->bi_status = BLK_STS_IOERR;
 			md_write_end(conf->mddev);
-			bio_endio(bi);
+			bio_io_error(bi);
 			bi = nextbi;
 		}
 		if (bitmap_end)
@@ -3403,9 +3402,8 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 		       sh->dev[i].sector + STRIPE_SECTORS) {
 			struct bio *bi2 = r5_next_bio(bi, sh->dev[i].sector);
 
-			bi->bi_status = BLK_STS_IOERR;
 			md_write_end(conf->mddev);
-			bio_endio(bi);
+			bio_io_error(bi);
 			bi = bi2;
 		}
 
@@ -3429,8 +3427,7 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 				struct bio *nextbi =
 					r5_next_bio(bi, sh->dev[i].sector);
 
-				bi->bi_status = BLK_STS_IOERR;
-				bio_endio(bi);
+				bio_io_error(bi);
 				bi = nextbi;
 			}
 		}
@@ -6237,6 +6234,8 @@ static void raid5_do_work(struct work_struct *work)
 	pr_debug("%d stripes handled\n", handled);
 
 	spin_unlock_irq(&conf->device_lock);
+
+	async_tx_issue_pending_all();
 	blk_finish_plug(&plug);
 
 	pr_debug("--- raid5worker inactive\n");